Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 10603
    Prev
    Next
    INDEX
    Explanations

    specific names and entities mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    historical references to significant figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utterstock
    -0.90
    izontal
    -0.86
    iculty
    -0.84
    pection
    -0.77
    vc
    -0.76
    iminary
    -0.75
    atown
    -0.74
     reuse
    -0.74
     indic
    -0.72
    giene
    -0.72
    POSITIVE LOGITS
     Barack
    1.37
     Adolf
    1.31
     Bashar
    1.30
     Winston
    1.30
     Donald
    1.28
     Osama
    1.27
     LeBron
    1.26
     George
    1.26
     Muhammad
    1.25
     Vladimir
    1.25
    Activations Density 1.292%

    No Known Activations